dolphin-2.9.1-yi-1.5-34b
01-aiapache-2.0text

dolphin-2.9.1-yi-1.5-34b

Updated Jun 7, 2026
Parameters
34.4B
Context
8,192
License
apache-2.0
Updated
Jun 7, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q4_K_M
1 of 4 quantizations fit dolphin-2.9.1-yi-1.5-34b with real runtime overhead.
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve dphn/dolphin-2.9.1-yi-1.5-34b

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

dolphin-2.9.1-yi-1.5-34b

dolphin-2.9.1-yi-1.5-34b is a 34.4B-parameter apache-2.0 model from dphn. At Q4_K_M it needs roughly 20 GB of VRAM, placing it in the 12-24gb hardware tier.

Specifications

SpecValue
Parameters34.4B
Context length8K tokens
Licenseapache-2.0
Modalitiestext
Released2024-05-18
Weightsdphn/dolphin-2.9.1-yi-1.5-34b

VRAM requirements

QuantVRAMRuns on
Q4_K_M~20 GBRTX 3090, RTX 4090
Q5_K_M~24 GBRTX 3090, RTX 4090
Q8_0~37 GBRTX 6000 Ada, dual RTX 3090
FP16~69 GBA100 80GB, H100

VRAM is estimated from parameter count; MoE models still need all weights resident.

How to run

vLLM:

vllm serve dphn/dolphin-2.9.1-yi-1.5-34b

Popularity

dolphin-2.9.1-yi-1.5-34b has 4,725,661 downloads in the last month on HuggingFace and 64 likes.

Frequently asked

Quick answers to common questions

How much VRAM does dolphin-2.9.1-yi-1.5-34b need?

dolphin-2.9.1-yi-1.5-34b with 34.4B parameters needs approximately 20 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is dolphin-2.9.1-yi-1.5-34b better than other 01-ai models?

dolphin-2.9.1-yi-1.5-34b has 34.4B parameters with 8,192 context - a strong choice for general use.

What license is dolphin-2.9.1-yi-1.5-34b under?

dolphin-2.9.1-yi-1.5-34b is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs dolphin-2.9.1-yi-1.5-34b well?

With 34.4B parameters, dolphin-2.9.1-yi-1.5-34b requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for dolphin-2.9.1-yi-1.5-34b?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~24 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with dolphin-2.9.1-yi-1.5-34b?

dolphin-2.9.1-yi-1.5-34b competes with other 17B–52B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.